© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3308
    Prev
    Next
    INDEX
    Explanations

    references to specific ethnicities or cultural identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and named entities referring to geographic locations and ethnic groups.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.70
     ModelExpression
    -0.53
     للمعارف
    -0.52
    AccessorTable
    -0.49
    -------
    -0.47
     comps
    -0.47
    makeConstraints
    -0.45
     compr
    -0.44
    IndentedString
    -0.44
    Vidite
    -0.44
    POSITIVE LOGITS
     Albanian
    0.88
     Albania
    0.81
     Kosovo
    0.73
     Tirana
    0.72
     alban
    0.69
    Albania
    0.68
     Alban
    0.68
    Alban
    0.66
    🇽
    0.54
     Gj
    0.52
    Activations Density 0.022%

    No Known Activations